Driver's Licensure and Driving Outcomes Among Youths With Mood Disorders.

Importance: Mood disorders are prevalent among adolescents and young adults, and their onset often coincides with driving eligibility. The understanding of how mood disorders are associated with youth driving outcomes is limited. Objective: To examine the association between the presence of a mood disorder and rates of licensing, crashes, violations, and suspensions among adolescents and young adults. Design, Setting, and Participants: This cohort study was conducted among New Jersey residents who were born 1987 to 2000, age eligible to acquire a driver's license from 2004 to 2017, and patients of the Children's Hospital of Philadelphia network within 2 years of licensure eligibility at age 17 years. The presence of a current (ie, ≤2 years of driving eligibility) mood disorder was identified using International Classification of Diseases, Ninth Revision, Clinical Modification (ICD-9-CM) or International Statistical Classification of Diseases, Tenth Revision, Clinical Modification (ICD-10-CM) codes. Rates of licensure and driving outcomes among youths who were licensed were compared among 1879 youths with and 84 294 youths without a current mood disorder from 2004 to 2017. Data were analyzed from June 2022 to July 2023. Main Outcomes and Measures: Acquisition of a driver's license and first involvement as a driver in a police-reported crash and rates of other adverse driving outcomes were assessed. Survival analysis was used to estimate adjusted hazard ratios (aHRs) for licensing and driving outcomes. Adjusted rate ratios (aRRs) were estimated for driving outcomes 12 and 48 months after licensure. Results: Among 86 173 youths (median [IQR] age at the end of the study, 22.8 [19.7-26.5] years; 42 894 female [49.8%]), there were 1879 youths with and 84 294 youths without a mood disorder. A greater proportion of youths with mood disorders were female (1226 female [65.2%]) compared with those without mood disorders (41 668 female [49.4%]). At 48 months after licensure eligibility, 75.5% (95% CI, 73.3%-77.7%) and 83.8% (95% CI, 83.5%-84.1%) of youths with and without mood disorders, respectively, had acquired a license. Youths with mood disorders were 30% less likely to acquire a license than those without a mood disorder (aHR, 0.70 [95% CI, 0.66-0.74]). Licensed youths with mood disorders had higher overall crash rates than those without mood disorders over the first 48 months of driving (137.8 vs 104.8 crashes per 10 000 driver-months; aRR, 1.19 [95% CI, 1.08-1.31]); licensed youths with mood disorders also had higher rates of moving violations (aRR, 1.25 [95% CI, 1.13-1.38]) and license suspensions (aRR, 1.95 [95% CI, 1.53-2.49]). Conclusions and Relevance: This study found that youths with mood disorders were less likely to be licensed and had higher rates of adverse driving outcomes than youths without mood disorders. These findings suggest that opportunities may exist to enhance driving mobility in this population and elucidate the mechanisms by which mood disorders are associated with crash risk.

The association between disability and all-cause mortality in low-income and middle-income countries: a systematic review and meta-analysis.

BACKGROUND: There are 1·3 billion people with disabilities globally. On average, they have poorer health than their non-disabled peers, but the extent of increased risk of premature mortality is unknown. We aimed to systematically review the association between disability and mortality in low-income and middle-income countries (LMICs). METHODS: We searched MEDLINE, Global Health, PsycINFO, and EMBASE from Jan 1, 1990 to Nov 14, 2022. Longitudinal epidemiological studies in any language with a comparator group that measured the association between disability and all-cause mortality in people of any age were eligible for inclusion. Two reviewers independently assessed study eligibility, extracted data, and assessed risk of bias. We used a random-effects meta-analysis to calculate the pooled hazard ratio (HR) for all-cause mortality by disability status. We then conducted meta-analyses separately for different impairment and age groups. FINDINGS: We identified 6146 unique articles, of which 70 studies (81 cohorts) were included in the systematic review, from 22 countries. There was variability in the methods used to assess and report disability and mortality. The meta-analysis included 54 studies, representing 62 cohorts (comprising 270 571 people with disabilities). Pooled HRs for all-cause mortality were 2·02 (95% CI 1·77-2·30) for people with disabilities versus those without disabilities, with high heterogeneity between studies (τ2=0·23, I2=98%). This association varied by impairment type: from 1·36 (1·17-1·57) for visual impairment to 3·95 (1·60-9·74) for multiple impairments. The association was highest for children younger than 18 years (4·46, [3·01-6·59]) and lower in people aged 15-49 years (2·45 [1·21-4·97]) and people older than 60 years (1·97 [1·65-2·36]). INTERPRETATION: People with disabilities had a two-fold higher mortality rate than people without disabilities in LMICs. Interventions are needed to improve the health of people with disabilities and reduce their higher mortality rate. FUNDING: UK National Institute for Health and Care Research; and UK Foreign, Commonwealth and Development Office.

Reproductive Planning: Short-Acting Reversible Contraceptives.

Short-acting reversible contraceptives (SARCs) are prescribed routinely by primary care clinicians. SARCs are among the most commonly prescribed contraceptive methods and include combined hormonal oral contraceptive pills, the combined hormonal transdermal patch, the combined hormonal vaginal ring, progestin-only pills, and the 3-month depot medroxyprogesterone acetate injection. To ensure safe prescribing and reduce barriers to receiving SARC methods, family physicians should be familiar with two evidence-based national contraceptive guidelines, the U.S. Medical Eligibility Criteria for Contraceptive Use (U.S. MEC) and the U.S. Selected Practice Recommendations for Contraceptive Use (U.S. SPR). SARCs have benefits in addition to pregnancy prevention; as such, these methods may be chosen for reasons other than contraception.

Sociotechnical feasibility of natural language processing-driven tools in clinical trial eligibility prescreening for Alzheimer's disease and related dementias.

BACKGROUND: Alzheimer's disease and related dementias (ADRD) affect over 55 million globally. Current clinical trials suffer from low recruitment rates, a challenge potentially addressable via natural language processing (NLP) technologies for researchers to effectively identify eligible clinical trial participants. OBJECTIVE: This study investigates the sociotechnical feasibility of NLP-driven tools for ADRD research prescreening and analyzes the tools' cognitive complexity's effect on usability to identify cognitive support strategies. METHODS: A randomized experiment was conducted with 60 clinical research staff using three prescreening tools (Criteria2Query, Informatics for Integrating Biology and the Bedside [i2b2], and Leaf). Cognitive task analysis was employed to analyze the usability of each tool using the Health Information Technology Usability Evaluation Scale. Data analysis involved calculating descriptive statistics, interrater agreement via intraclass correlation coefficient, cognitive complexity, and Generalized Estimating Equations models. RESULTS: Leaf scored highest for usability followed by Criteria2Query and i2b2. Cognitive complexity was found to be affected by age, computer literacy, and number of criteria, but was not significantly associated with usability. DISCUSSION: Adopting NLP for ADRD prescreening demands careful task delegation, comprehensive training, precise translation of eligibility criteria, and increased research accessibility. The study highlights the relevance of these factors in enhancing NLP-driven tools' usability and efficacy in clinical research prescreening. CONCLUSION: User-modifiable NLP-driven prescreening tools were favorably received, with system type, evaluation sequence, and user's computer literacy influencing usability more than cognitive complexity. The study emphasizes NLP's potential in improving recruitment for clinical trials, endorsing a mixed-methods approach for future system evaluation and enhancements.

Health literacy in the context of child health promotion: a scoping review of conceptualizations and descriptions.

BACKGROUND: Increasing health literacy (HL) in children could be an opportunity for a more health literate future generation. The aim of this scoping review is to provide an overview of how HL is conceptualized and described in the context of health promotion in 9-12-year-old children. METHODS: A systematic and comprehensive search for 'health literacy' and 'children' and 'measure' was performed in accordance with PRISMA ScR in PubMed, Embase.com and via Ebsco in CINAHL, APA PsycInfo and ERIC. Two reviewers independently screened titles and abstracts and evaluated full-text publications regarding eligibility. Data was extracted systematically, and the extracted descriptions of HL were analyzed qualitatively using deductive analysis based on previously published HL definitions. RESULTS: The search provided 5,401 original titles, of which 26 eligible publications were included. We found a wide variation of descriptions of learning outcomes as well as competencies for HL. Most HL descriptions could be linked to commonly used definitions of HL in the literature, and some combined several HL dimensions. The descriptions varied between HL dimensions and were not always relevant to health promotion. The educational setting plays a prominent role in HL regarding health promotion. CONCLUSION: The description of HL is truly diverse and complex encompassing a wide range of topics. We recommend adopting a comprehensive and integrated approach to describe HL dimensions, particularly in the context of health promotion for children. By considering the diverse dimensions of HL and its integration within educational programs, children can learn HL skills and competencies from an early age.

COVID-19 Medicaid Continuous Enrollment Provision Yielded Gains In Postpartum Continuity Of Coverage.

The Medicaid continuous enrollment provision mandated by the Families First Coronavirus Response Act of 2020 effectively prohibited the termination of enrollees from Medicaid during the COVID-19 public health emergency, including people enrolled in Medicaid during pregnancy. Using data from the Transformed Medicaid Statistical Information System, we found that the rate of continuous Medicaid enrollment during the twelve months postpartum increased from 59.3 percent for births during March-December 2018 to 90.7 percent for births during March-December 2020, when the public health emergency was in effect. This corresponds to approximately 430,000 fewer people losing Medicaid coverage after pregnancy and an average of more than 2.5 months of additional postpartum enrollment. These findings indicate that states that have extended or that plan to extend pregnancy-related Medicaid eligibility in the postpartum year are likely to experience significant gains in continuity of coverage.

Predictors of COVID-19 vaccine uptake: an online three-wave survey study of US adults.

BACKGROUND: To effectively promote vaccine uptake, it is important to understand which people are most and least inclined to be vaccinated and why. In this study, we examined predictors of COVID-19 vaccine uptake and reasons for non-vaccination. METHODS: We conducted an online English-language survey study in December-2020, January-2021, and March-2021. A total of 930 US respondents completed all surveys. Multiple logistic regression models were run to test whether the early vaccine eligibility, demographic factors, and psychological factors predict getting at least one dose of a COVID-19 vaccination in January-2021 and in March-2021. RESULTS: The proportion of respondents who received ≥ 1-dose of a COVID-19 vaccine increased from 18% (January) to 67% (March). Older age predicted vaccine uptake in January (OR = 2.02[95%CI = 1.14-3.78], p < .001) and March (10.92[6.76-18.05], p < .001). In January, additional predictors were higher numeracy (1.48[1.20-1.86], p < .001), COVID-19 risk perceptions (1.35[1.03-1.78], p = .029), and believing it is important adults get the COVID-19 vaccine (1.66[1.05-2.66], p = .033). In March, additional predictors of uptake were believing it is important adults get the COVID-19 vaccine (1.63[1.15-2.34], p = .006), prior COVID-19 vaccine intentions (1.37[1.10-1.72], p = .006), and belief in science (0.84[0.72-0.99], p = .041). Concerns about side effects and the development process were the most common reasons for non-vaccination. Unvaccinated respondents with no interest in getting a COVID-19 vaccine were younger (0.27[0.09-0.77], p = .016), held negative views about COVID-19 vaccines for adults (0.15[0.08-0.26], p < .001), had lower trust in healthcare (0.59[0.36-0.95], p = .032), and preferred to watch and wait in clinically ambiguous medical situations (0.66[0.48-0.89], p = .007). CONCLUSIONS: Evidence that attitudes and intentions towards COVID-19 vaccines were important predictors of uptake provides validation for studies using these measures and reinforces the need to develop strategies for addressing safety and development concerns which remain at the forefront of vaccine hesitancy.

Association between racial iniquities and oral health status: a systematic review. / Associação entre iniquidades raciais e condição de saúde bucal: revisão sistemática.

The present study aimed to investigate the association between racial iniquities and oral health status. This is a systematic review with a protocol registered on the Prospero Platform (CRD42021228417), with searches carried out in electronic databases and in gray literature. Our study identified 3,028 publications. After applying the eligibility criteria and risk of bias analysis, 18 studies were selected. The results indicate that individuals of black/brown race/skin color have unfavorable oral health conditions, mainly represented by self-rated oral health, tooth loss, caries, and periodontitis. The results showed racial iniquities in oral health in different countries, for all analyzed indicators, with a greater vulnerability of the black population.

O objetivo deste estudo é investigar a associação entre iniquidades raciais e condição de saúde bucal. Trata-se de revisão sistemática com protocolo cadastrado na plataforma prospero (CRD42021228417), com buscas realizadas em bases de dados eletrônicas e na literatura cinzenta. Identificou-se 3.028 publicações e após aplicação dos critérios de elegibilidade e análise do risco de vieses, 18 estudos foram selecionados. Os resultados indicam que indivíduos de raça/cor da pele preta/parda apresentam condições de saúde bucal desfavorável, representada principalmente pela autoavaliação de saúde bucal, perda dentária, cárie e periodontite. Os resultados evidenciaram iniquidades raciais em saúde bucal em diferentes países, para todos os indicadores analisados, com maior vulnerabilidade da população negra.

Interest in mHealth Among Patients With Low Back Pain: Cross-Sectional Study.

BACKGROUND: Digitally supported self-management tailored to an individual's need, in addition to usual care, may reduce pain-related disability compared to usual care alone, and patients with low back pain (LBP) using mobile health (mHealth) solutions express positive experiences. Hence, implementing mHealth solutions designed to support self-management is desirable from a clinical and patient perspective. Easily accessible mHealth solutions that can support the self-management of patients with LBP are available, but interest may be subgroup specific. Understanding the characteristics and preferences of patients with LBP labeled as interested may help to reach relevant LBP patient groups and inform the development and implementation of effective interventions with mHealth for patients with LBP. OBJECTIVE: This study aims to explore the proportion of patients with LBP labeled as interested in testing an mHealth solution designed to support self-management in addition to usual care and to assess how these patients differ from those who were labeled as not interested. METHODS: This exploratory cross-sectional study analyzed demographic and patient-reported outcomes from the SpineData registry, a Danish registry of patients with LBP in an outpatient setting. Between February and December 2019, the SpineData registry was used to assess the preliminary eligibility of patients for a clinical trial (selfBACK). Patients were labeled as interested or uninterested depending on if they responded to an invitation to be tested for eligibility for the trial Outcomes were selected from the International Classification of Functioning core set of LBP using a clinical approach. Associations were assessed in a backward selection process, and the proportion of variance explained was assessed with pseudo-R2 statistic. RESULTS: This study included 843 patients, with 181 (21%) individuals labeled as interested in participating in the selfBACK trial. Notably, the cohort labeled as interested differed from their uninterested counterparts in two key aspects: age (36-65 years: 116/181, 64.1% vs 347/662, 52.4%; P=.003) and smoking status (smokers: 22/181, 12.5% vs 174/662, 26.6%; P<.001). Those aged 36-65 years had higher odds of being labeled as interested compared to individuals aged 18-35 years (odds ratio [OR] 0.43, 95% CI 0.26-0.71) and those 65 years or older (OR 0.77, 95% CI 0.53-1.15). Nevertheless, age accounted for only a modest proportion of variance (R2=0.014). Smokers demonstrated lower odds of being labeled as interested (OR 0.39, 95% CI 0.24-0.64), with smoking status explaining a similarly small proportion of variance (R2=0.019). Collectively, age and smoking status accounted for 3.3% of the variance. CONCLUSIONS: Our investigation revealed that 181 (21%) individuals with LBP invited to participate in the mHealth solution trial for self-management expressed interest. Generally, the characteristics of those labeled as interested and uninterested were comparable. Of note, patients aged 36-65 years had a higher frequency of being labeled as interested compared to their younger and older counterparts.

Medicare Part D low-income subsidies expanded in January 2024, but more needs to be done to ensure that eligible beneficiaries enroll.

BACKGROUND: The Inflation Reduction Act of 2022 extended full low-income subsidies (LIS) to a small group of Medicare Part D recipients with limited assets and incomes between 135% and 150% of the Federal Poverty Level beginning in January 2024. This policy may result in small enrollment gains among beneficiaries eligible for the new benefits, but the biggest problem with the current LIS program is underenrollment across all eligibility groups. Prior research has shown that underenrollment has been a persistent problem since the LIS program began in 2006, yet little has been done to correct the situation. OBJECTIVE: To identify individual-level factors associated with failure to enroll among low-income beneficiaries eligible for both full subsidies and partial subsidies under the LIS program. METHODS: We used 2019 Medicare Current Beneficiary Survey data for the study. The Medicare Current Beneficiary Survey is uniquely suited for this work because it contains administrative data on LIS enrollment plus extensive survey information on financial resources necessary to establish program eligibility. We conducted descriptive and multivariate analyses to identify factors associated with failure to enroll when eligible for either full or partial subsidies. Explanatory variables included sociodemographic characteristics, economic resources, work status, health variables, and source of prescription coverage (for nonsubsidized beneficiaries). RESULTS: In 2019, 73% of beneficiaries eligible for full subsidies under pre-Inflation Reduction Act LIS provisions were enrolled, compared with only 25% eligible for partial subsidies. The number of those estimated to be eligible for full subsidies but not enrolled (N = 3.9 million) was more than double that of those eligible but not enrolled for partial subsidies (N = 1.5 million). Factors associated with failure to enroll (older age, male sex, White race, married, higher education, higher income and assets, and excellent/very good health status) were similar for both groups. In multivariate analyses, the single strongest predictor of failure to enroll was receipt of income from work (odds ratio = 5.50; P < 0.001). Among the nonenrolled, 64% eligible for full subsidies and 75% eligible for partial subsidies maintained unsubsidized Part D coverage. CONCLUSIONS: Significant numbers of low-income Medicare beneficiaries are eligible for Part D subsidies but fail to enroll. Common characteristics distinguishing nonenrollees from enrollees include older age with higher proportions of White individuals, married individuals, higher income and assets, and better overall health. Two promising targets for increasing LIS enrollment are evidence of work income and unsubsidized Part D coverage.

Medicare Eligibility and Reported Support for Proposals to Expand Medicare.

This study estimates the association between Medicare eligibility and support for recent proposals to expand program participation and benefits.

The effect of Medicare eligibility on diagnosis of chronic conditions.

OBJECTIVES: The near-universal access to Medicare coverage at age 65 years improves access to care. However, little is known about whether Medicare eligibility promotes the diagnosis of chronic diseases. We examined the effects of Medicare eligibility at age 65 years on the diagnosis of chronic conditions. STUDY DESIGN: Using data from the 2007-2019 Medical Expenditure Panel Survey, we employed a regression discontinuity design. METHODS: Our sample includes 43,620 individuals aged 59 to 71 years. Our primary outcomes were diagnoses of 19 chronic conditions. Using a regression discontinuity design, we exploited the discontinuity in eligibility for Medicare at age 65 years and compared individuals just before and after age 65 years. RESULTS: Medicare eligibility at age 65 years led to significant increases in having any coverage or Medicare coverage: 8.8 percentage points (95% CI, 8.4-9.2) and 78.1 percentage points (95% CI, 74.9-81.4), respectively. However, there were no or small changes in the diagnosis of chronic conditions at age 65 years. Specifically, there were no significant changes in the diagnoses of 17 chronic conditions, and the changes were minor in magnitude. Significant changes were observed only in the diagnosis of stroke and cancer, at -0.6 percentage points (95% CI, -1.0 to -0.2) and -1.7 percentage points (95% CI, -2.8 to -0.6), respectively. CONCLUSIONS: Our findings suggest that Medicare coverage did not necessarily lead to increased diagnosis of chronic conditions. Further research is necessary to explore the underlying mechanisms behind this observation.

The effects of medication therapy management on medication utilization among Medicare beneficiaries with HIV/AIDS.

BACKGROUND: Medicare Part D plans are required to provide medication therapy management (MTM) programs to eligible beneficiaries to optimize medication utilization. MTM programs' effects on medication utilization among older persons living with HIV/AIDS (PLWHs) remain unclear. OBJECTIVE: This study examined the effects of the Medicare MTM programs on medication utilization among PLWHs. METHODS: This study analyzed 2017 Medicare databases linked to the Area Health Resources Files. Recipients and nonrecipients of the MTM services were compared on their medication utilization: adherence to antiretroviral medications, drug-drug interactions (DDI), and concurrent use of opioids and benzodiazepines. The intervention group comprised recipients of the MTM services, and the control group was nonrecipients meeting the eligibility criteria. A propensity score with a ratio of 1:2 between the intervention and control groups was used to identify study groups with balanced characteristics. A logistic regression was used to control for patient/community characteristics. RESULTS: After matching, the intervention and comparison groups comprised 3298 and 6596 beneficiaries for the antiretroviral adherence measure, 809 and 1618 for the DDI measure, and 691 and 1382 for the concurrent use of opioids and benzodiazepines measure. The intervention was associated with higher odds of adherence to antiretroviral medications (adjusted odds ratio = 1.15, 95% CI = 1.04-1.26), and no concurrent use of opioids and benzodiazepines (adjusted odds ratio = 1.255, 95% CI = 1.005-1.568). The study groups did not differ on no DDI (adjusted odds ratio = 0.95, 95% CI = 0.74-1.20). CONCLUSIONS: Medicare MTM programs effectively improved medication utilization among PLWHs. Future studies should explore the long-term effects of the program.

Commercial provider staff experiences of the NHS low calorie diet programme pilot: a qualitative exploration of key barriers and facilitators.

BACKGROUND: The National Health Service Type 2 Diabetes Path to Remission programme in England (known as the NHS Low Calorie Diet programme when piloted) was established to support people living with excess weight and Type 2 Diabetes to lose weight and improve their glycaemic control. A mixed method evaluation was commissioned to provide an enhanced understanding of the long-term cost effectiveness of the pilot programme, its implementation, equity and transferability across broad and diverse populations. This study provided key insights on implementation and equity from the service providers' perspective. METHODS: Thirteen focus groups were conducted with commercial providers of the programme, during the initial pilot rollout. Participants were purposively sampled across all provider organisations and staff roles involved in implementing and delivering the programme. Normalisation Process Theory (NPT) was used to design the topic schedule, with the addition of topics on equity and person-centredness. Data were thematically analysed using NPT constructs with additional inductively created codes. Codes were summarised, and analytical themes generated. RESULTS: The programme was found to fulfil the requirements for normalisation from the providers' perspective. However, barriers were identified in engaging GP practices and receiving sufficient referrals, as well as supporting service users through challenges to remain compliant. There was variation in communication and training between provider sites. Areas for learning and improvement included adapting systems and processes and closing the gap where needs of service users are not fully met. CONCLUSIONS: The evaluation of the pilot programme demonstrated that it was workable when supported by effective primary care engagement, comprehensive training, and effective internal and external communication. However, limitations were identified in relation to programme specifications e.g. eligibility criteria, service specification and local commissioning decisions e.g. pattern of roll out, incentivisation of general practice. A person-centred approach to care is fundamental and should include cultural adaptation(s), and the assessment and signposting to additional support and services where required.

Comparison performance of the Bayesian Approach with the Weibull and Birnbaum-Saunders distributions in imputation of time-to-event censors.

Almost all survival data is censored, and censor imputation is necessary. This study aimed to investigate the performance of the Bayesian Approach (BA) in the imputation of censored records in simulated and Breast Cancer (BC) data. Due to the difference in the distribution of time to event in survival analysis, two well-known the Weibull and Birnbaum-Saunders (BS) distributions have been used to test the performance of the BA. For each of the censored, 10,000 times were simulated using the BA in R and BUGS software, and their median or mean was imputed instead of each censor. The eligibility of both imputation methods was investigated using different curves, different censoring percentages, and sample sizes, as well as the Deviance Information Criteria (DIC), Effective Sample Size, and the Geweke diagnostic in simulated and especially real BC data. The BC data, which contains 220 patients who were identified and followed up between 2015 and 2023, was made accessible on February 1, 2023. The Kaplan-Meier, the BA, and other survival curves were drawn for the observed times. Findings indicated that the performance of the BA under the Weibull and BS distributions in simulated data is similar. The DIC index in the BC data under the BS distribution (1510) is less than the Weibull distribution (1698). Therefore, the BS distribution is preferred over the Weibull for imputation of censoring times in real BC data.

End Users' Perceived Engagement with Clinical Dashboards: A Rapid Review.

Clinical dashboards are an emerging and fast-evolving technology used to support frontline clinicians' practice. Understanding end users' perceived engagement with clinical dashboards is essential to co-design, implementation, and adoption. There is a lack of literature exploring the integration of dashboards into clinical workflow. This rapid review explores clinical end users' perceived engagement with dashboards that support workflow. We conducted a literature search in PubMed and CINAHL. Four articles met our eligibility criteria. Findings reveal variations in taxonomy and measures used to evaluate clinicians' perceived engagement. There are also a variety of reported barriers and facilitators to adoption. Standardized frameworks and vocabulary are needed to facilitate a common understanding of clinical end users' perceived engagement with dashboards.

Matching Patients to Accelerate Clinical Trials (MPACT): Enabling Technology for Oncology Clinical Trial Workflow.

Clinical trial enrollment is impeded by the significant time burden placed on research coordinators screening eligible patients. With 50,000 new cancer cases every year, the Veterans Health Administration (VHA) has made increased access for Veterans to high-quality clinical trials a priority. To aid in this effort, we worked with research coordinators to build the MPACT (Matching Patients to Accelerate Clinical Trials) platform with a goal of improving efficiency in the screening process. MPACT supports both a trial prescreening workflow and a screening workflow, employing Natural Language Processing and Data Science methods to produce reliable phenotypes of trial eligibility criteria. MPACT also has a functionality to track a patient's eligibility status over time. Qualitative feedback has been promising with users reporting a reduction in time spent on identifying eligible patients.

Implementation of Artificial Intelligence Applications in Australian Healthcare Organisations: Environmental Scan Findings.

Artificial Intelligence (AI) has great potential to improve healthcare, but implementation into routine practice remains a challenge. This study scoped the extent to which AI and Natural Language Processing (NLP) is being implemented into routine practice in Australian healthcare organisations. An environmental scan of publicly available data was undertaken to identify AI applications. Publicly available data consisted of news posts from Australian public healthcare organisations and conference proceedings from key research organisations. Two researchers reviewed and analysed posts related to AI applications to create a list of potential implementation case studies. The final list of AI applications was reviewed by a governance committee in order to identify any missing applications. One application was identified by the governance committee and subsequently added. The environmental scan identified eighteen AI applications, of which eleven met all eligibility criteria. Only one application included NLP. Twelve applications were included when the application identified by the governance committee was added to the list. Implementation of AI applications is spread across four broad categories of use: 1) Decision Support, 2) Monitoring Treatment Effectiveness, 3) Personalised Care and 4) Risk Prediction.